Plausible Patients, Impossible Populations: Auditing Epidemiological Fidelity in Large Language Model Mental Health Simulations
Language models asked to simulate psychiatric patients produce cases that survive inspection one at a time and populations that match no real one. We gave GPT-4o-mini, Gemini-3-Flash, DeepSeek-V3 and GLM-4.7 each of 120 demographic cohorts under two framings, one written as a clinician enters a patient and one as a person describes themselves, and scored all 28,800 responses against survey-weighted PHQ-8 anchors derived from NHANES microdata. Case by case the output holds up: 97.3% of elevated presentations satisfy the DSM-5 gateway rule, violating it at 2.68% against a chance null of 10.4%. As populations, four things fail at once. Every benchmarkable group returns inflated by 2.8 to 5.5 PHQ-8 points, and 18.2% of simulated patients screen at the treatment threshold against 7.5% of adults. Population Black-White and Hispanic-White disparities do not survive the simulation, with two models attenuating each gap and two flattening or inverting it. Symptom covariance reorganizes by cohort, putting the error beyond any recalibration, and demographic offsets do not stack, so a correction fitted on marginals misses the cells by about 0.4 points either way. And the answer does not hold still: at the decoding a deployment inherits, a third of patients change severity category between two draws of one prompt and one in five crosses the line from watchful waiting to treatment. We read the four together as one failure, and name the gap between case-level plausibility and population-level failure the coherence-fidelity dissociation. Individual cases clear a formal rule a case review would apply; the populations they compose fail every comparison we can construct against a real one. Gender identity carries an extreme on both symptom structure and regeneration stability, and no federal benchmark exists to check any of it. The patients look right. They do not represent real populations.